Phota Edit API Documentation

Phota Edit API Documentation

Playground

Phota Edit transforms existing images using natural language instructions. Supports up to 10 reference images, 1K and 4K resolutions, and batch output up to 4 images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Phota Edit is an AI-powered image editing model that transforms photos using natural language instructions. Describe the change you want — swap clothing, alter backgrounds, adjust styles, add or remove objects — and the model applies precise, context-aware edits while preserving the rest of the image. Supports multiple input images, batch output, and flexible aspect ratio control.

Why Choose This?

• Natural-language editing Describe your edit in plain text — no masks, no manual selections, no technical knowledge required.

• Multi-image input Upload multiple reference images to provide richer visual context for complex edits.

• 4K output support Generate high-resolution edited results for print, production, or archival use.

• Flexible aspect ratio control Output in auto, 1:1, 16:9, 4:3, 3:4, or 9:16 to match your target platform.

• Multiple output formats Export in JPEG, PNG, or WebP for any downstream workflow.

• Batch output Generate multiple edited variations in a single run using the num_images parameter.

Parameters

How to Use

1. Write your prompt — describe exactly what should change in the image (e.g., “Change the man’s clothes to beach casual wear and put on sunglasses.”).
2. Upload your image(s) — provide one or more source images via URL or drag-and-drop. Click Add Item to add more.
3. Select resolution — 1K for standard output, 4K for high-resolution results.
4. Set num_images (optional) — generate multiple variations in one run.
5. Choose aspect ratio — use auto to preserve the source ratio, or select a specific format.
6. Choose output format — jpeg, png, or webp based on your delivery needs.
7. Submit — generate and download your edited image.

Pricing

Billing Rules

• 1K: $0.09 per image
• 4K: $0.18 per image (2× base price)
• Total cost = cost per image × num_images

Best Use Cases

• Fashion & Apparel — Swap clothing, accessories, or outfit styles on model photos without reshooting.
• E-commerce — Edit product images to showcase different colors, settings, or variants from a single source.
• Marketing & Advertising — Update visual assets quickly — change backgrounds, props, or styling to match campaign needs.
• Portrait Retouching — Make targeted appearance changes while preserving the overall look and feel.
• Creative Concepting — Rapidly iterate on visual ideas and styling directions for client review.

Pro Tips

• Be specific and descriptive in your prompt — the more detail you provide, the more accurate the edit.
• Upload multiple images when you want the model to reference additional context, such as a target style or specific elements.
• Use 4K output for final production assets and 1K for rapid iteration and testing.
• Use PNG output for lossless results when editing images with text, graphics, or sharp edges.
• Enable sync mode in API workflows where you need the result returned directly without polling.

Notes

• Only prompt is required; all other parameters are optional.
• Ensure image URLs are publicly accessible if using links rather than direct uploads.
• Please ensure your content complies with WaveSpeed AI’s usage policies.

Related Models

• Phota Enhance — Restore and upscale images without editing using AI-powered detail reconstruction.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "resolution": "1K",
  "num_images": 1,
  "aspect_ratio": "auto",
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/phota/edit" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters